Learning Bill Similarity with Annotated and Augmented Corpora of Bills
This work addresses the need for better understanding bill-to-bill linkages in legislative processes, though it is incremental as it builds on existing BERT variants and focuses on a domain-specific application.
The paper tackles the problem of identifying semantic similarities between legislative bills, which often involve reordering and paraphrasing, by proposing a 5-class classification task and constructing a human-labeled dataset of 4,721 bill-to-bill relationships. The result shows that predictive performance significantly improves when training with both human-labeled and synthetic data, and the methodology successfully captures similarities at various aggregation levels.
Bill writing is a critical element of representative democracy. However, it is often overlooked that most legislative bills are derived, or even directly copied, from other bills. Despite the significance of bill-to-bill linkages for understanding the legislative process, existing approaches fail to address semantic similarities across bills, let alone reordering or paraphrasing which are prevalent in legal document writing. In this paper, we overcome these limitations by proposing a 5-class classification task that closely reflects the nature of the bill generation process. In doing so, we construct a human-labeled dataset of 4,721 bill-to-bill relationships at the subsection-level and release this annotated dataset to the research community. To augment the dataset, we generate synthetic data with varying degrees of similarity, mimicking the complex bill writing process. We use BERT variants and apply multi-stage training, sequentially fine-tuning our models with synthetic and human-labeled datasets. We find that the predictive performance significantly improves when training with both human-labeled and synthetic data. Finally, we apply our trained model to infer section- and bill-level similarities. Our analysis shows that the proposed methodology successfully captures the similarities across legal documents at various levels of aggregation.